July 29, 2019

2827 words 14 mins read

Paper Group ANR 43

A Novel Approach to Artistic Textual Visualization via GAN. A Variational EM Method for Pole-Zero Modeling of Speech with Mixed Block Sparse and Gaussian Excitation. Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations. Methods for applying the Neural Engineering Framework to neuromorphic hardware. Automatic Breast U …

A Novel Approach to Artistic Textual Visualization via GAN


Title	A Novel Approach to Artistic Textual Visualization via GAN
Authors	Yichi Ma, Muhan Ma
Abstract	While the visualization of statistical data tends to a mature technology, the visualization of textual data is still in its infancy, especially for the artistic text. Due to the fact that visualization of artistic text is valuable and attractive in both art and information science, we attempt to realize this tentative idea in this article. We propose the Generative Adversarial Network based Artistic Textual Visualization (GAN-ATV) which can create paintings after analyzing the semantic content of existing poems. Our GAN-ATV consists of two main sections: natural language analysis section and visual information synthesis section. In natural language analysis section, we use Bag-of-Word (BoW) feature descriptors and a two-layer network to mine and analyze the high-level semantic information from poems. In visual information synthesis section, we design a cross-modal semantic understanding module and integrate it with Generative Adversarial Network (GAN) to create paintings, whose content are corresponding to the original poems. Moreover, in order to train our GAN-ATV and verify its performance, we establish a cross-modal artistic dataset named “Cross-Art”. In the Cross-Art dataset, there are six topics and each topic has their corresponding paintings and poems. The experimental results on Cross-Art dataset are shown in this article.
Tasks
Published	2017-10-29
URL	http://arxiv.org/abs/1710.10553v1
PDF	http://arxiv.org/pdf/1710.10553v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-approach-to-artistic-textual
Repo
Framework

A Variational EM Method for Pole-Zero Modeling of Speech with Mixed Block Sparse and Gaussian Excitation


Title	A Variational EM Method for Pole-Zero Modeling of Speech with Mixed Block Sparse and Gaussian Excitation
Authors	Liming Shi, Jesper Kjær Nielsen, Jesper Rindom Jensen, Mads Græsbøll Christensen
Abstract	The modeling of speech can be used for speech synthesis and speech recognition. We present a speech analysis method based on pole-zero modeling of speech with mixed block sparse and Gaussian excitation. By using a pole-zero model, instead of the all-pole model, a better spectral fitting can be expected. Moreover, motivated by the block sparse glottal flow excitation during voiced speech and the white noise excitation for unvoiced speech, we model the excitation sequence as a combination of block sparse signals and white noise. A variational EM (VEM) method is proposed for estimating the posterior PDFs of the block sparse residuals and point estimates of mod- elling parameters within a sparse Bayesian learning framework. Compared to conventional pole-zero and all-pole based methods, experimental results show that the proposed method has lower spectral distortion and good performance in reconstructing of the block sparse excitation.
Tasks	Speech Recognition, Speech Synthesis
Published	2017-06-24
URL	http://arxiv.org/abs/1706.07927v1
PDF	http://arxiv.org/pdf/1706.07927v1.pdf
PWC	https://paperswithcode.com/paper/a-variational-em-method-for-pole-zero
Repo
Framework

Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations


Title	Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations
Authors	Benjamin J. Lengerich, Andrew L. Maas, Christopher Potts
Abstract	Knowledge graphs are a versatile framework to encode richly structured data relationships, but it can be challenging to combine these graphs with unstructured data. Methods for retrofitting pre-trained entity representations to the structure of a knowledge graph typically assume that entities are embedded in a connected space and that relations imply similarity. However, useful knowledge graphs often contain diverse entities and relations (with potentially disjoint underlying corpora) which do not accord with these assumptions. To overcome these limitations, we present Functional Retrofitting, a framework that generalizes current retrofitting methods by explicitly modeling pairwise relations. Our framework can directly incorporate a variety of pairwise penalty functions previously developed for knowledge graph completion. Further, it allows users to encode, learn, and extract information about relation semantics. We present both linear and neural instantiations of the framework. Functional Retrofitting significantly outperforms existing retrofitting methods on complex knowledge graphs and loses no accuracy on simpler graphs (in which relations do imply similarity). Finally, we demonstrate the utility of the framework by predicting new drug–disease treatment pairs in a large, complex health knowledge graph.
Tasks	Knowledge Graph Completion, Knowledge Graphs
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00112v3
PDF	http://arxiv.org/pdf/1708.00112v3.pdf
PWC	https://paperswithcode.com/paper/retrofitting-distributional-embeddings-to
Repo
Framework

Methods for applying the Neural Engineering Framework to neuromorphic hardware


Title	Methods for applying the Neural Engineering Framework to neuromorphic hardware
Authors	Aaron R. Voelker, Chris Eliasmith
Abstract	We review our current software tools and theoretical methods for applying the Neural Engineering Framework to state-of-the-art neuromorphic hardware. These methods can be used to implement linear and nonlinear dynamical systems that exploit axonal transmission time-delays, and to fully account for nonideal mixed-analog-digital synapses that exhibit higher-order dynamics with heterogeneous time-constants. This summarizes earlier versions of these methods that have been discussed in a more biological context (Voelker & Eliasmith, 2017) or regarding a specific neuromorphic architecture (Voelker et al., 2017).
Tasks
Published	2017-08-27
URL	http://arxiv.org/abs/1708.08133v1
PDF	http://arxiv.org/pdf/1708.08133v1.pdf
PWC	https://paperswithcode.com/paper/methods-for-applying-the-neural-engineering
Repo
Framework

Automatic Breast Ultrasound Image Segmentation: A Survey


Title	Automatic Breast Ultrasound Image Segmentation: A Survey
Authors	Min Xian, Yingtao Zhang, H. D. Cheng, Fei Xu, Boyu Zhang, Jianrui Ding
Abstract	Breast cancer is one of the leading causes of cancer death among women worldwide. In clinical routine, automatic breast ultrasound (BUS) image segmentation is very challenging and essential for cancer diagnosis and treatment planning. Many BUS segmentation approaches have been studied in the last two decades, and have been proved to be effective on private datasets. Currently, the advancement of BUS image segmentation seems to meet its bottleneck. The improvement of the performance is increasingly challenging, and only few new approaches were published in the last several years. It is the time to look at the field by reviewing previous approaches comprehensively and to investigate the future directions. In this paper, we study the basic ideas, theories, pros and cons of the approaches, group them into categories, and extensively review each category in depth by discussing the principles, application issues, and advantages/disadvantages.
Tasks	Semantic Segmentation
Published	2017-04-04
URL	http://arxiv.org/abs/1704.01472v2
PDF	http://arxiv.org/pdf/1704.01472v2.pdf
PWC	https://paperswithcode.com/paper/automatic-breast-ultrasound-image
Repo
Framework

Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics


Title	Analysis of feature detector and descriptor combinations with a localization experiment for various performance metrics
Authors	Ertugrul Bayraktar, Pinar Boyraz
Abstract	The purpose of this study is to provide a detailed performance comparison of feature detector/descriptor methods, particularly when their various combinations are used for image-matching. The localization experiments of a mobile robot in an indoor environment are presented as a case study. In these experiments, 3090 query images and 127 dataset images were used. This study includes five methods for feature detectors (features from accelerated segment test (FAST), oriented FAST and rotated binary robust independent elementary features (BRIEF) (ORB), speeded-up robust features (SURF), scale invariant feature transform (SIFT), and binary robust invariant scalable keypoints (BRISK)) and five other methods for feature descriptors (BRIEF, BRISK, SIFT, SURF, and ORB). These methods were used in 23 different combinations and it was possible to obtain meaningful and consistent comparison results using the performance criteria defined in this study. All of these methods were used independently and separately from each other as either feature detector or descriptor. The performance analysis shows the discriminative power of various combinations of detector and descriptor methods. The analysis is completed using five parameters: (i) accuracy, (ii) time, (iii) angle difference between keypoints, (iv) number of correct matches, and (v) distance between correctly matched keypoints. In a range of 60{\deg}, covering five rotational pose points for our system, the FAST-SURF combination had the lowest distance and angle difference values and the highest number of matched keypoints. SIFT-SURF was the most accurate combination with a 98.41% correct classification rate. The fastest algorithm was ORB-BRIEF, with a total running time of 21,303.30 s to match 560 images captured during motion with 127 dataset images.
Tasks
Published	2017-10-17
URL	http://arxiv.org/abs/1710.06232v1
PDF	http://arxiv.org/pdf/1710.06232v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-feature-detector-and-descriptor
Repo
Framework

On the Challenges of Detecting Rude Conversational Behaviour


Title	On the Challenges of Detecting Rude Conversational Behaviour
Authors	Karan Grewal, Khai N. Truong
Abstract	In this study, we aim to identify moments of rudeness between two individuals. In particular, we segment all occurrences of rudeness in conversations into three broad, distinct categories and try to identify each. We show how machine learning algorithms can be used to identify rudeness based on acoustic and semantic signals extracted from conversations. Furthermore, we make note of our shortcomings in this task and highlight what makes this problem inherently difficult. Finally, we provide next steps which are needed to ensure further success in identifying rudeness in conversations.
Tasks
Published	2017-12-28
URL	http://arxiv.org/abs/1712.09929v1
PDF	http://arxiv.org/pdf/1712.09929v1.pdf
PWC	https://paperswithcode.com/paper/on-the-challenges-of-detecting-rude
Repo
Framework

Partial Transfer Learning with Selective Adversarial Networks


Title	Partial Transfer Learning with Selective Adversarial Networks
Authors	Zhangjie Cao, Mingsheng Long, Jianmin Wang, Michael I. Jordan
Abstract	Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. Existing domain adversarial networks assume fully shared label space across domains. In the presence of big data, there is strong motivation of transferring both classification and representation models from existing big domains to unknown small domains. This paper introduces partial transfer learning, which relaxes the shared label space assumption to that the target label space is only a subspace of the source label space. Previous methods typically match the whole source domain to the target domain, which are prone to negative transfer for the partial transfer problem. We present Selective Adversarial Network (SAN), which simultaneously circumvents negative transfer by selecting out the outlier source classes and promotes positive transfer by maximally matching the data distributions in the shared label space. Experiments demonstrate that our models exceed state-of-the-art results for partial transfer learning tasks on several benchmark datasets.
Tasks	Transfer Learning
Published	2017-07-25
URL	http://arxiv.org/abs/1707.07901v1
PDF	http://arxiv.org/pdf/1707.07901v1.pdf
PWC	https://paperswithcode.com/paper/partial-transfer-learning-with-selective
Repo
Framework

Rational Choice and Artificial Intelligence


Title	Rational Choice and Artificial Intelligence
Authors	Tshilidzi Marwala
Abstract	The theory of rational choice assumes that when people make decisions they do so in order to maximize their utility. In order to achieve this goal they ought to use all the information available and consider all the choices available to choose an optimal choice. This paper investigates what happens when decisions are made by artificially intelligent machines in the market rather than human beings. Firstly, the expectations of the future are more consistent if they are made by an artificially intelligent machine and the decisions are more rational and thus marketplace becomes more rational.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.10098v1
PDF	http://arxiv.org/pdf/1703.10098v1.pdf
PWC	https://paperswithcode.com/paper/rational-choice-and-artificial-intelligence
Repo
Framework

Learning to Adapt by Minimizing Discrepancy


Title	Learning to Adapt by Minimizing Discrepancy
Authors	Alexander G. Ororbia II, Patrick Haffner, David Reitter, C. Lee Giles
Abstract	We explore whether useful temporal neural generative models can be learned from sequential data without back-propagation through time. We investigate the viability of a more neurocognitively-grounded approach in the context of unsupervised generative modeling of sequences. Specifically, we build on the concept of predictive coding, which has gained influence in cognitive science, in a neural framework. To do so we develop a novel architecture, the Temporal Neural Coding Network, and its learning algorithm, Discrepancy Reduction. The underlying directed generative model is fully recurrent, meaning that it employs structural feedback connections and temporal feedback connections, yielding information propagation cycles that create local learning signals. This facilitates a unified bottom-up and top-down approach for information transfer inside the architecture. Our proposed algorithm shows promise on the bouncing balls generative modeling problem. Further experiments could be conducted to explore the strengths and weaknesses of our approach.
Tasks
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11542v1
PDF	http://arxiv.org/pdf/1711.11542v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-adapt-by-minimizing-discrepancy
Repo
Framework

Semantic Image Retrieval via Active Grounding of Visual Situations


Title	Semantic Image Retrieval via Active Grounding of Visual Situations
Authors	Max H. Quinn, Erik Conser, Jordan M. Witte, Melanie Mitchell
Abstract	We describe a novel architecture for semantic image retrieval—in particular, retrieval of instances of visual situations. Visual situations are concepts such as “a boxing match,” “walking the dog,” “a crowd waiting for a bus,” or “a game of ping-pong,” whose instantiations in images are linked more by their common spatial and semantic structure than by low-level visual similarity. Given a query situation description, our architecture—called Situate—learns models capturing the visual features of expected objects as well the expected spatial configuration of relationships among objects. Given a new image, Situate uses these models in an attempt to ground (i.e., to create a bounding box locating) each expected component of the situation in the image via an active search procedure. Situate uses the resulting grounding to compute a score indicating the degree to which the new image is judged to contain an instance of the situation. Such scores can be used to rank images in a collection as part of a retrieval system. In the preliminary study described here, we demonstrate the promise of this system by comparing Situate’s performance with that of two baseline methods, as well as with a related semantic image-retrieval system based on “scene graphs.”
Tasks	Image Retrieval
Published	2017-10-31
URL	http://arxiv.org/abs/1711.00088v1
PDF	http://arxiv.org/pdf/1711.00088v1.pdf
PWC	https://paperswithcode.com/paper/semantic-image-retrieval-via-active-grounding
Repo
Framework

A dependency look at the reality of constituency


Title	A dependency look at the reality of constituency
Authors	Xinying Chen, Carlos Gómez-Rodríguez, Ramon Ferrer-i-Cancho
Abstract	A comment on “Neurophysiological dynamics of phrase-structure building during sentence processing” by Nelson et al (2017), Proceedings of the National Academy of Sciences USA 114(18), E3669-E3678.
Tasks
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07722v3
PDF	http://arxiv.org/pdf/1708.07722v3.pdf
PWC	https://paperswithcode.com/paper/a-dependency-look-at-the-reality-of
Repo
Framework

Non-Asymptotic Uniform Rates of Consistency for k-NN Regression


Title	Non-Asymptotic Uniform Rates of Consistency for k-NN Regression
Authors	Heinrich Jiang
Abstract	We derive high-probability finite-sample uniform rates of consistency for $k$-NN regression that are optimal up to logarithmic factors under mild assumptions. We moreover show that $k$-NN regression adapts to an unknown lower intrinsic dimension automatically. We then apply the $k$-NN regression rates to establish new results about estimating the level sets and global maxima of a function from noisy observations.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06261v2
PDF	http://arxiv.org/pdf/1707.06261v2.pdf
PWC	https://paperswithcode.com/paper/non-asymptotic-uniform-rates-of-consistency
Repo
Framework

Deep Voice 2: Multi-Speaker Neural Text-to-Speech


Title	Deep Voice 2: Multi-Speaker Neural Text-to-Speech
Authors	Sercan Arik, Gregory Diamos, Andrew Gibiansky, John Miller, Kainan Peng, Wei Ping, Jonathan Raiman, Yanqi Zhou
Abstract	We introduce a technique for augmenting neural text-to-speech (TTS) with lowdimensional trainable speaker embeddings to generate different voices from a single model. As a starting point, we show improvements over the two state-ofthe-art approaches for single-speaker neural TTS: Deep Voice 1 and Tacotron. We introduce Deep Voice 2, which is based on a similar pipeline with Deep Voice 1, but constructed with higher performance building blocks and demonstrates a significant audio quality improvement over Deep Voice 1. We improve Tacotron by introducing a post-processing neural vocoder, and demonstrate a significant audio quality improvement. We then demonstrate our technique for multi-speaker speech synthesis for both Deep Voice 2 and Tacotron on two multi-speaker TTS datasets. We show that a single neural TTS system can learn hundreds of unique voices from less than half an hour of data per speaker, while achieving high audio quality synthesis and preserving the speaker identities almost perfectly.
Tasks	Speech Synthesis
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08947v2
PDF	http://arxiv.org/pdf/1705.08947v2.pdf
PWC	https://paperswithcode.com/paper/deep-voice-2-multi-speaker-neural-text-to
Repo
Framework

A Deep Belief Network Based Machine Learning System for Risky Host Detection


Title	A Deep Belief Network Based Machine Learning System for Risky Host Detection
Authors	Wangyan Feng, Shuning Wu, Xiaodan Li, Kevin Kunkle
Abstract	To assure cyber security of an enterprise, typically SIEM (Security Information and Event Management) system is in place to normalize security event from different preventive technologies and flag alerts. Analysts in the security operation center (SOC) investigate the alerts to decide if it is truly malicious or not. However, generally the number of alerts is overwhelming with majority of them being false positive and exceeding the SOC’s capacity to handle all alerts. There is a great need to reduce the false positive rate as much as possible. While most previous research focused on network intrusion detection, we focus on risk detection and propose an intelligent Deep Belief Network machine learning system. The system leverages alert information, various security logs and analysts’ investigation results in a real enterprise environment to flag hosts that have high likelihood of being compromised. Text mining and graph based method are used to generate targets and create features for machine learning. In the experiment, Deep Belief Network is compared with other machine learning algorithms, including multi-layer neural network, random forest, support vector machine and logistic regression. Results on real enterprise data indicate that the deep belief network machine learning system performs better than other algorithms for our problem and is six times more effective than current rule-based system. We also implement the whole system from data collection, label creation, feature engineering to host score generation in a real enterprise production environment.
Tasks	Feature Engineering, Intrusion Detection, Network Intrusion Detection
Published	2017-12-29
URL	http://arxiv.org/abs/1801.00025v1
PDF	http://arxiv.org/pdf/1801.00025v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-belief-network-based-machine-learning
Repo
Framework